cmpoumpousis | 13 Oct 14:00 2008
Picon

Bad Quality in a Greek LPC Diphone voice

Hello everyone,

I have created a Greek LPC diphone voice but the prosody is really bad. The
phoneme junctures are ok, which means that the labeling and the segmentation is
ok. So i think that the pitchmark extraction is problematic. I have uploaded
some samples of the voice in the following link in order to check them out if
you have time and verify my assumption.

http://rapidshare.com/files/153562517/Eval.rar.html

Thank you very much in advance,

Chris Boubousis

===========================================
Boubousis Chris
Undergraduate Student

Speech Group
Telecom Laboratory
Department of Electronics & Computer Engineering
Technical University of Crete
Chania 73100, Greece

Nickolay V. Shmyrev | 13 Oct 22:19 2008
Picon

Re: Bad Quality in a Greek LPC Diphone voice

В Пнд, 13/10/2008 в 15:00 +0300, cmpoumpousis <at> telecom.tuc.gr пишет:
> Hello everyone,
> 
> I have created a Greek LPC diphone voice but the prosody is really bad. The
> phoneme junctures are ok, which means that the labeling and the segmentation is
> ok. So i think that the pitchmark extraction is problematic. I have uploaded
> some samples of the voice in the following link in order to check them out if
> you have time and verify my assumption.
> 
> http://rapidshare.com/files/153562517/Eval.rar.html
> 
> Thank you very much in advance,

Well, f0 is certainly wrong. Please provide a sample wav file from your
database, a corresponding pitchark file and also please provide an
utterance which you can get with 

(utt.save (SayText "some text"))

Firoj Alam | 20 Oct 11:08 2008
Picon

Building automatic LTS rule. Any guide for unicode?

I am trying to build automatic LTS rule for "Bangla TTS". I have lexicon data in unicode format. The automatic LTS developing tool which is available in festival does not work for unicode. But general lts.ruleset can handle unicode by reading three byte as a [one unicode] character. Is there any way to make/modify the system [lts_build], which can handle the unicode.

Regards
Firoj

Send instant messages to your online friends http://uk.messenger.yahoo.com
Alan W Black | 20 Oct 13:54 2008
Picon

Re: Building automatic LTS rule. Any guide for unicode?

Firoj Alam wrote:
> I am trying to build automatic LTS rule for "Bangla TTS". I have lexicon data in unicode format. The
automatic LTS developing tool which is available in festival does not work for unicode. But general
lts.ruleset can handle unicode by reading three byte as a [one unicode] character. Is there any way to
make/modify the system [lts_build], which can handle the unicode.
> 

Hi Firoj,

Yes it does work with unicode but you need to be a little careful at the 
first state.  However instead of having your initial lexicon as

( "LLLLLL" nil (p p p p p p p))

If you have

( ("L" "L" "L" "L" "L") nil (p p p p p p p)

Where "LLLLL" is a unicode word and "L" "L" "L" ... are the unicode 
split letters.

In the latest version of the LTS scripts in festvox/src/lts, the
setup option can take a third argument asis or utf8 which should make it 
do the right thing with utf8

$FESTVOXDIR/src/lts/build_lts setup yourlex.scm utf8

This has worked for lots of languages including Hindi/Devanagari.

Alan

> Regards
> Firoj
> 
> 
> Send instant messages to your online friends http://uk.messenger.yahoo.com 

Firoj Alam | 21 Oct 11:32 2008
Picon

Re: Building automatic LTS rule. Any guide for unicode?

Thanks Alan.

May be i'm missing something. The system showing the following error.

#####Error#########
murtoza <at> murtoza-desktop:~/Desktop$ $FESTVOXDIR/src/lts/build_lts setup lex.scm utf8
SIOD ERROR: not a symbol or string : ("ক")
closing a file left open: lts_scratch/lex_entries.out
closing a file left open: lex.scm
murtoza <at> murtoza-desktop:~/Desktop$

#################

My lexicon file contains the following:

MNCL
(("ক") nil ( k a ) )
(("ক" "ই") nil (k o i ) )
(("ক" "ই" "ত" "র") nil ( k o i ta a r ) )


Even i tried on English [(("k") nil ( k a ) )] but having the same error.


Regards
Firoj
----- Original Message ----
From: Alan W Black <awb-ETDLCGt7PQU3uPMLIKxrzw@public.gmane.org>
To: Firoj Alam <firojalam04-/E1597aS9LQAvxtiuMwx3w@public.gmane.org>
Cc: festivox <festvox-talk-UtUuZmX9S4RAfugRpC6u6w@public.gmane.org>
Sent: Monday, 20 October, 2008 17:54:16
Subject: Re: Building automatic LTS rule. Any guide for unicode?

Hi Firoj,

Yes it does work with unicode but you need to be a little careful at the
first state.  However instead of having your initial lexicon as

( "LLLLLL" nil (p p p p p p p))

If you have

( ("L" "L" "L" "L" "L") nil (p p p p p p p)

Where "LLLLL" is a unicode word and "L" "L" "L" ... are the unicode
split letters.

In the latest version of the LTS scripts in festvox/src/lts, the
setup option can take a third argument asis or utf8 which should make it
do the right thing with utf8

$FESTVOXDIR/src/lts/build_lts setup yourlex.scm utf8

This has worked for lots of languages including Hindi/Devanagari.

Alan


> Regards
> Firoj
>
>
> Send instant messages to your online friends http://uk.messenger.yahoo.com



Gmane